Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask5_holistic

This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 18.8520
  • Qwk: 0.4271
  • Mse: 18.8521
  • Rmse: 4.3419

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.0198 2 309.5754 -0.0008 309.5754 17.5948
No log 0.0396 4 297.2239 0.0063 297.2239 17.2402
No log 0.0594 6 276.0659 0.0005 276.0659 16.6152
No log 0.0792 8 260.9591 0.0058 260.9591 16.1542
No log 0.0990 10 245.5980 0.0019 245.5980 15.6716
No log 0.1188 12 236.4712 0.0019 236.4712 15.3776
No log 0.1386 14 224.0879 0.0079 224.0879 14.9696
No log 0.1584 16 211.0043 0.0018 211.0043 14.5260
No log 0.1782 18 202.4148 0.0106 202.4148 14.2273
No log 0.1980 20 194.1026 0.0076 194.1026 13.9321
No log 0.2178 22 188.1413 0.0082 188.1413 13.7165
No log 0.2376 24 179.0470 0.0083 179.0471 13.3808
No log 0.2574 26 169.4088 0.0068 169.4088 13.0157
No log 0.2772 28 164.3105 0.0010 164.3105 12.8184
No log 0.2970 30 163.4389 0.0011 163.4389 12.7843
No log 0.3168 32 155.5291 0.0005 155.5291 12.4711
No log 0.3366 34 149.4123 0.0107 149.4123 12.2234
No log 0.3564 36 145.7011 0.0053 145.7011 12.0707
No log 0.3762 38 142.7275 0.0020 142.7275 11.9469
No log 0.3960 40 137.0045 0.0012 137.0045 11.7049
No log 0.4158 42 132.9291 0.0006 132.9291 11.5295
No log 0.4356 44 130.2772 0.0090 130.2772 11.4139
No log 0.4554 46 127.6222 0.0065 127.6222 11.2970
No log 0.4752 48 123.4366 0.0019 123.4366 11.1102
No log 0.4950 50 120.1826 0.0007 120.1826 10.9628
No log 0.5149 52 118.4731 0.0014 118.4731 10.8845
No log 0.5347 54 119.1399 0.0014 119.1399 10.9151
No log 0.5545 56 112.9749 0.0 112.9749 10.6290
No log 0.5743 58 110.9021 0.0113 110.9021 10.5310
No log 0.5941 60 110.8386 0.0057 110.8386 10.5280
No log 0.6139 62 106.7876 0.0035 106.7876 10.3338
No log 0.6337 64 104.7523 0.0016 104.7523 10.2349
No log 0.6535 66 103.2511 0.0016 103.2510 10.1613
No log 0.6733 68 103.5874 0.0016 103.5874 10.1778
No log 0.6931 70 99.9350 0.0 99.9350 9.9967
No log 0.7129 72 98.0992 0.0 98.0992 9.9045
No log 0.7327 74 98.0432 0.0 98.0432 9.9017
No log 0.7525 76 94.9331 0.0 94.9331 9.7434
No log 0.7723 78 93.2257 0.0216 93.2257 9.6553
No log 0.7921 80 91.8215 0.0048 91.8215 9.5824
No log 0.8119 82 90.7648 0.0019 90.7648 9.5271
No log 0.8317 84 88.5899 0.0010 88.5899 9.4122
No log 0.8515 86 87.4155 0.0010 87.4155 9.3496
No log 0.8713 88 86.2485 0.0 86.2485 9.2870
No log 0.8911 90 83.4863 0.0 83.4863 9.1371
No log 0.9109 92 81.8508 0.0 81.8508 9.0471
No log 0.9307 94 80.8622 0.0 80.8622 8.9923
No log 0.9505 96 79.2444 0.0 79.2444 8.9019
No log 0.9703 98 78.4342 0.0090 78.4342 8.8563
No log 0.9901 100 76.6547 0.0073 76.6547 8.7553
No log 1.0099 102 75.5856 0.0023 75.5856 8.6940
No log 1.0297 104 74.7172 0.0023 74.7172 8.6439
No log 1.0495 106 73.3267 0.0012 73.3267 8.5631
No log 1.0693 108 72.4987 0.0012 72.4987 8.5146
No log 1.0891 110 72.0991 0.0 72.0991 8.4911
No log 1.1089 112 70.7042 0.0 70.7042 8.4086
No log 1.1287 114 70.1797 0.0 70.1797 8.3773
No log 1.1485 116 69.1484 0.0 69.1484 8.3155
No log 1.1683 118 68.4735 0.0 68.4735 8.2749
No log 1.1881 120 67.6425 0.0 67.6425 8.2245
No log 1.2079 122 66.9049 0.0 66.9049 8.1795
No log 1.2277 124 66.4505 0.0 66.4505 8.1517
No log 1.2475 126 65.4911 0.0 65.4911 8.0927
No log 1.2673 128 64.8073 0.0010 64.8073 8.0503
No log 1.2871 130 63.9728 0.0147 63.9728 7.9983
No log 1.3069 132 63.7242 0.0061 63.7242 7.9827
No log 1.3267 134 62.4046 0.0028 62.4046 7.8997
No log 1.3465 136 61.7069 0.0028 61.7069 7.8554
No log 1.3663 138 61.1325 0.0015 61.1325 7.8187
No log 1.3861 140 60.9453 0.0015 60.9453 7.8067
No log 1.4059 142 59.7199 0.0 59.7199 7.7279
No log 1.4257 144 59.4352 0.0 59.4352 7.7094
No log 1.4455 146 58.7446 0.0 58.7446 7.6645
No log 1.4653 148 58.3918 0.0 58.3918 7.6415
No log 1.4851 150 58.4205 0.0 58.4205 7.6433
No log 1.5050 152 57.0442 0.0 57.0442 7.5528
No log 1.5248 154 56.5059 0.0 56.5059 7.5170
No log 1.5446 156 55.9161 0.0 55.9161 7.4777
No log 1.5644 158 55.5239 0.0 55.5239 7.4514
No log 1.5842 160 54.9079 0.0 54.9079 7.4100
No log 1.6040 162 54.2922 0.0 54.2922 7.3683
No log 1.6238 164 53.7075 0.0 53.7075 7.3285
No log 1.6436 166 53.1748 0.0 53.1748 7.2921
No log 1.6634 168 52.7802 0.0252 52.7802 7.2650
No log 1.6832 170 52.4909 0.0120 52.4909 7.2451
No log 1.7030 172 51.7312 0.0209 51.7312 7.1924
No log 1.7228 174 51.2649 0.0234 51.2649 7.1599
No log 1.7426 176 50.8058 0.0270 50.8058 7.1278
No log 1.7624 178 50.2658 0.0185 50.2658 7.0898
No log 1.7822 180 49.9836 0.0116 49.9836 7.0699
No log 1.8020 182 49.0522 0.0260 49.0522 7.0037
No log 1.8218 184 48.5062 0.0353 48.5062 6.9646
No log 1.8416 186 47.9199 0.0203 47.9199 6.9224
No log 1.8614 188 47.4385 0.0132 47.4385 6.8876
No log 1.8812 190 46.9314 0.0185 46.9314 6.8506
No log 1.9010 192 46.6479 0.0289 46.6479 6.8299
No log 1.9208 194 46.1093 0.0138 46.1093 6.7904
No log 1.9406 196 46.0725 0.0074 46.0725 6.7877
No log 1.9604 198 45.4341 0.0074 45.4341 6.7405
No log 1.9802 200 44.9375 0.0229 44.9375 6.7035
No log 2.0 202 44.3466 0.0185 44.3466 6.6593
No log 2.0198 204 43.8551 0.0154 43.8551 6.6223
No log 2.0396 206 43.3851 0.0224 43.3851 6.5867
No log 2.0594 208 42.9520 0.0657 42.9520 6.5538
No log 2.0792 210 43.3767 0.0011 43.3767 6.5861
No log 2.0990 212 43.1984 0.0077 43.1984 6.5726
No log 2.1188 214 41.9803 0.0843 41.9803 6.4792
No log 2.1386 216 43.1696 0.1002 43.1696 6.5704
No log 2.1584 218 41.3614 0.0629 41.3614 6.4313
No log 2.1782 220 42.9506 0.0118 42.9506 6.5537
No log 2.1980 222 41.6856 0.0042 41.6856 6.4564
No log 2.2178 224 41.4918 0.0042 41.4918 6.4414
No log 2.2376 226 41.0008 0.0042 41.0008 6.4032
No log 2.2574 228 40.7052 0.0042 40.7052 6.3801
No log 2.2772 230 40.3244 0.0042 40.3244 6.3501
No log 2.2970 232 39.9954 0.0069 39.9954 6.3242
No log 2.3168 234 39.6921 0.0179 39.6921 6.3002
No log 2.3366 236 39.1860 0.0292 39.1860 6.2599
No log 2.3564 238 38.9961 0.1065 38.9961 6.2447
No log 2.3762 240 38.3462 0.1439 38.3462 6.1924
No log 2.3960 242 39.0171 0.2027 39.0171 6.2464
No log 2.4158 244 38.2401 0.1218 38.2401 6.1839
No log 2.4356 246 38.8355 0.0619 38.8355 6.2318
No log 2.4554 248 37.0752 0.1063 37.0752 6.0889
No log 2.4752 250 37.4128 0.1440 37.4128 6.1166
No log 2.4950 252 36.7900 0.0992 36.7900 6.0655
No log 2.5149 254 36.6525 0.0577 36.6525 6.0541
No log 2.5347 256 36.7457 0.0332 36.7457 6.0618
No log 2.5545 258 36.2507 0.0443 36.2507 6.0209
No log 2.5743 260 35.9432 0.1152 35.9432 5.9953
No log 2.5941 262 36.4604 0.1678 36.4604 6.0382
No log 2.6139 264 36.6238 0.1966 36.6238 6.0518
No log 2.6337 266 34.8506 0.1331 34.8506 5.9034
No log 2.6535 268 35.1787 0.1234 35.1787 5.9312
No log 2.6733 270 35.3829 0.0907 35.3829 5.9484
No log 2.6931 272 34.7041 0.0725 34.7041 5.8910
No log 2.7129 274 33.8906 0.1795 33.8906 5.8216
No log 2.7327 276 34.3079 0.2043 34.3079 5.8573
No log 2.7525 278 33.8451 0.2038 33.8451 5.8177
No log 2.7723 280 33.5473 0.1205 33.5473 5.7920
No log 2.7921 282 33.4275 0.1206 33.4275 5.7817
No log 2.8119 284 33.0182 0.1386 33.0182 5.7461
No log 2.8317 286 32.5695 0.2038 32.5695 5.7070
No log 2.8515 288 33.1291 0.2588 33.1291 5.7558
No log 2.8713 290 33.7284 0.2859 33.7284 5.8076
No log 2.8911 292 31.7837 0.2190 31.7837 5.6377
No log 2.9109 294 31.7370 0.1815 31.7370 5.6336
No log 2.9307 296 31.2718 0.2131 31.2718 5.5921
No log 2.9505 298 31.9096 0.2826 31.9096 5.6489
No log 2.9703 300 34.2613 0.3302 34.2613 5.8533
No log 2.9901 302 32.4780 0.3119 32.4780 5.6989
No log 3.0099 304 31.1234 0.2764 31.1234 5.5788
No log 3.0297 306 30.8723 0.1747 30.8723 5.5563
No log 3.0495 308 30.9972 0.1306 30.9972 5.5675
No log 3.0693 310 30.3700 0.1223 30.3700 5.5109
No log 3.0891 312 29.6756 0.1855 29.6756 5.4475
No log 3.1089 314 29.6392 0.2029 29.6392 5.4442
No log 3.1287 316 29.2692 0.1840 29.2692 5.4101
No log 3.1485 318 29.2276 0.2127 29.2276 5.4063
No log 3.1683 320 29.0946 0.2071 29.0946 5.3939
No log 3.1881 322 28.9436 0.2073 28.9436 5.3799
No log 3.2079 324 28.7824 0.2068 28.7824 5.3649
No log 3.2277 326 28.8763 0.1808 28.8763 5.3737
No log 3.2475 328 28.7095 0.1644 28.7095 5.3581
No log 3.2673 330 28.2242 0.1921 28.2242 5.3126
No log 3.2871 332 28.2748 0.2484 28.2748 5.3174
No log 3.3069 334 30.9103 0.3146 30.9103 5.5597
No log 3.3267 336 30.2156 0.3067 30.2156 5.4969
No log 3.3465 338 29.2744 0.3411 29.2744 5.4106
No log 3.3663 340 28.0127 0.3339 28.0126 5.2927
No log 3.3861 342 27.7211 0.3126 27.7211 5.2651
No log 3.4059 344 27.5057 0.2873 27.5057 5.2446
No log 3.4257 346 27.2753 0.2774 27.2753 5.2226
No log 3.4455 348 26.9787 0.2670 26.9787 5.1941
No log 3.4653 350 26.6971 0.2616 26.6971 5.1669
No log 3.4851 352 26.4867 0.2563 26.4867 5.1465
No log 3.5050 354 26.2979 0.2628 26.2979 5.1281
No log 3.5248 356 26.1192 0.2795 26.1192 5.1107
No log 3.5446 358 25.9366 0.2864 25.9366 5.0928
No log 3.5644 360 25.8546 0.2607 25.8546 5.0847
No log 3.5842 362 25.8383 0.2411 25.8383 5.0831
No log 3.6040 364 25.5870 0.2602 25.5870 5.0584
No log 3.6238 366 25.4240 0.3260 25.4240 5.0422
No log 3.6436 368 28.7765 0.3995 28.7765 5.3644
No log 3.6634 370 26.8469 0.3900 26.8469 5.1814
No log 3.6832 372 24.9566 0.2808 24.9566 4.9957
No log 3.7030 374 25.9309 0.1588 25.9309 5.0922
No log 3.7228 376 26.1030 0.1299 26.1030 5.1091
No log 3.7426 378 25.7301 0.1442 25.7301 5.0725
No log 3.7624 380 25.1992 0.1677 25.1992 5.0199
No log 3.7822 382 24.7273 0.2045 24.7273 4.9727
No log 3.8020 384 24.4828 0.2220 24.4828 4.9480
No log 3.8218 386 24.1297 0.2474 24.1297 4.9122
No log 3.8416 388 23.9535 0.3069 23.9535 4.8942
No log 3.8614 390 24.1260 0.3399 24.1260 4.9118
No log 3.8812 392 23.7741 0.3201 23.7741 4.8759
No log 3.9010 394 23.7873 0.3287 23.7873 4.8772
No log 3.9208 396 23.8955 0.3429 23.8955 4.8883
No log 3.9406 398 23.7090 0.3318 23.7090 4.8692
No log 3.9604 400 23.3753 0.2821 23.3753 4.8348
No log 3.9802 402 23.5559 0.2202 23.5559 4.8534
No log 4.0 404 24.1653 0.1548 24.1653 4.9158
No log 4.0198 406 23.9141 0.1541 23.9141 4.8902
No log 4.0396 408 22.8191 0.3185 22.8191 4.7769
No log 4.0594 410 22.8555 0.3239 22.8555 4.7807
No log 4.0792 412 23.0660 0.2827 23.0660 4.8027
No log 4.0990 414 23.3739 0.2478 23.3739 4.8347
No log 4.1188 416 23.1660 0.2596 23.1660 4.8131
No log 4.1386 418 22.5233 0.3135 22.5233 4.7459
No log 4.1584 420 22.2283 0.3828 22.2283 4.7147
No log 4.1782 422 22.8994 0.4314 22.8994 4.7853
No log 4.1980 424 23.4053 0.4397 23.4053 4.8379
No log 4.2178 426 22.1264 0.3920 22.1264 4.7039
No log 4.2376 428 22.0891 0.3211 22.0891 4.6999
No log 4.2574 430 22.6933 0.2525 22.6933 4.7637
No log 4.2772 432 22.2051 0.2882 22.2051 4.7122
No log 4.2970 434 21.7056 0.3843 21.7056 4.6589
No log 4.3168 436 25.9793 0.4383 25.9793 5.0970
No log 4.3366 438 30.6833 0.3759 30.6833 5.5392
No log 4.3564 440 24.0529 0.3941 24.0529 4.9044
No log 4.3762 442 21.5641 0.3343 21.5641 4.6437
No log 4.3960 444 22.1054 0.2735 22.1054 4.7016
No log 4.4158 446 22.3390 0.2282 22.3390 4.7264
No log 4.4356 448 22.2024 0.2155 22.2024 4.7119
No log 4.4554 450 21.7558 0.2486 21.7558 4.6643
No log 4.4752 452 21.3179 0.3057 21.3179 4.6171
No log 4.4950 454 21.1084 0.3961 21.1084 4.5944
No log 4.5149 456 21.3566 0.4243 21.3566 4.6213
No log 4.5347 458 21.0966 0.4216 21.0966 4.5931
No log 4.5545 460 20.6978 0.3849 20.6978 4.5495
No log 4.5743 462 20.7784 0.3373 20.7784 4.5583
No log 4.5941 464 20.7080 0.3335 20.7080 4.5506
No log 4.6139 466 20.8587 0.2948 20.8587 4.5671
No log 4.6337 468 20.6551 0.3016 20.6551 4.5448
No log 4.6535 470 20.0688 0.3649 20.0688 4.4798
No log 4.6733 472 20.0323 0.4063 20.0323 4.4757
No log 4.6931 474 19.7728 0.3822 19.7728 4.4467
No log 4.7129 476 19.6981 0.3530 19.6981 4.4383
No log 4.7327 478 19.7190 0.3226 19.7190 4.4406
No log 4.7525 480 19.5528 0.3421 19.5528 4.4219
No log 4.7723 482 19.6562 0.4023 19.6562 4.4335
No log 4.7921 484 20.5863 0.4379 20.5863 4.5372
No log 4.8119 486 19.9522 0.4174 19.9522 4.4668
No log 4.8317 488 19.3624 0.3893 19.3624 4.4003
No log 4.8515 490 19.3898 0.3546 19.3898 4.4034
No log 4.8713 492 19.4415 0.3322 19.4415 4.4092
No log 4.8911 494 19.1464 0.3672 19.1464 4.3757
No log 4.9109 496 19.1896 0.4091 19.1896 4.3806
No log 4.9307 498 19.7081 0.5003 19.7081 4.4394
63.9533 4.9505 500 19.2302 0.5153 19.2302 4.3852
63.9533 4.9703 502 18.8754 0.4962 18.8754 4.3446
63.9533 4.9901 504 18.8562 0.4549 18.8562 4.3424
63.9533 5.0099 506 19.0290 0.4188 19.0290 4.3622
63.9533 5.0297 508 18.9686 0.4206 18.9686 4.3553
63.9533 5.0495 510 18.8520 0.4271 18.8521 4.3419

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
2
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MayBashendy/Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask5_holistic

Finetuned
(4019)
this model